Search papers, labs, and topics across Lattice.
3
0
5
Scaling task complexity across 280 standardized manipulation variants reveals that today's leading VLA models fundamentally collapse under fine-grained spatial ambiguity and memory-intensive sequential planning.
AWARe effectively preserves prior knowledge in MLLMs while boosting performance on new tasks, challenging the conventional trade-off between retention and adaptation.
UniPhysGen achieves state-of-the-art performance in grounding physical properties of 3D assets, enabling seamless integration into robotic simulations.
